#python #deep_learning #resnest #resnet

https://github.com/zhanghang1989/ResNeSt

#python #deep_neural_networks #deployment #detection #neural_networks #classification #segmentation #resnet #deeplearning #unet #industry #jetson #mobilenet #yolov3

https://github.com/PaddlePaddle/PaddleX

#cplusplus #vgg #resnet #alexnet #squeezenet #inceptionv3 #googlenet #resnext #tensorrt #crnn #senet #arcface #mobilenetv2 #yolov3 #shufflenetv2 #mnasnet #retinaface #mobilenetv3 #yolov3_spp #yolov4 #yolov5

https://github.com/wang-xinyu/tensorrtx

#python #deep_learning #image_classification #imagenet #mobilenet #pytorch #regnet #resnet #resnext #senet #shufflenet #swin_transformer

https://github.com/open-mmlab/mmclassification

#python #augmix #convnext #distributed_training #dual_path_networks #efficientnet #image_classification #imagenet #maxvit #mixnet #mobile_deep_learning #mobilenet_v2 #mobilenetv3 #nfnets #normalization_free_training #pretrained_models #pretrained_weights #pytorch #randaugment #resnet #vision_transformer_models

PyTorch Image Models (`timm`) is a comprehensive library that includes a wide range of state-of-the-art image models, layers, utilities, optimizers, and training scripts. Here are the key benefits `timm` offers over 300 pre-trained models from various families like Vision Transformers, ResNets, EfficientNets, and more, allowing you to choose the best model for your task.
- **Pre-trained Weights** You can easily extract features at different levels of the network using `features_only=True` and `out_indices`, making it versatile for various applications.
- **Optimizers and Schedulers** It provides several augmentation techniques like AutoAugment, RandAugment, and regularization methods like DropPath and DropBlock to enhance model performance.
- **Reference Training Scripts**: Included are high-performance training, validation, and inference scripts that support multiple GPUs and mixed-precision training.

Overall, `timm` simplifies the process of working with deep learning models for image tasks by providing a unified interface and extensive tools for training and evaluation.

https://github.com/huggingface/pytorch-image-models

#cplusplus #caffe #convolution #deep_learning #deep_neural_networks #diy #graph_algorithms #inference #inference_engine #maxpooling #ncnn #pnnx #pytorch #relu #resnet #sigmoid #yolo #yolov5

This course, "_动手自制大模型推理框架_" (Handcrafting Large Model Inference Framework), is a valuable resource for those interested in deep learning and model inference. It teaches you how to build a modern C++ project from scratch, focusing on designing and implementing a deep learning inference framework. The course supports latest models like LLama3.2 and Qwen2.5, and uses CUDA acceleration and Int8 quantization for better performance.

By taking this course, you will learn how to write efficient C++ code, manage projects with CMake and Git, design computational graphs, implement common operators like convolution and pooling, and optimize them for speed. This knowledge will be highly beneficial for job interviews and advancing your skills in deep learning. The course also includes practical demos on models like Unet and YoloV5, making it a hands-on learning experience.

https://github.com/zjhellofss/KuiperInfer

#cplusplus #accelerator #llama #llm #low_level_programming #metal #mistral #mixtral #ml #resnet #stable_diffusion #tenstorrent

Tenstorrent's TT-Metal is a powerful tool for developing AI models. It allows users to create custom kernels for their hardware, which can improve performance by reducing memory usage. This is especially useful for large language models (LLMs) like Llama and Mixtral. The TT-Metal system supports efficient data movement and computation, making it beneficial for users who need to run complex AI tasks quickly and effectively. By optimizing how data is stored and processed, TT-Metal helps users achieve better results with less effort.

https://github.com/tenstorrent/tt-metal